LLM EXPLORER 60,384 MODELS INDEXED

Qwen3.5 24.5B Reapped V1 by groxaxo

By groxaxo · 118 downloads
HF Repo ↗ Copy URL

Qwen3.5 24.5B Reapped V1 is an open-source language model by groxaxo. Features: 25.1b LLM, VRAM: 50.1GB, Context: 256K, License: apache-2.0, MoE, LLM Explorer Score: 0.25.

  Agentic   Coding   Conversational   En   Endpoints compatible   Lora   Lora-merged   Moe   Pruned   Qlora   Qwen3 5 moe   Qwen3 5 moe text   Reap   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/groxaxo/Qwen3.5-24.5B-Reapped-v1 

Qwen3.5 24.5B Reapped V1 Parameters and Internals

LLM NameQwen3.5 24.5B Reapped V1
Repository 🤗https://huggingface.co/groxaxo/Qwen3.5-24.5B-Reapped-v1 
Model Size25.1b
Required VRAM50.1 GB
Updated2026-08-04
Maintainergroxaxo
Model Typeqwen3_5_moe_text
Model Files  4.9 GB: 1-of-11   4.8 GB: 2-of-11   4.8 GB: 3-of-11   4.8 GB: 4-of-11   4.8 GB: 5-of-11   4.8 GB: 6-of-11   4.8 GB: 7-of-11   4.8 GB: 8-of-11   4.8 GB: 9-of-11   4.8 GB: 10-of-11   2.0 GB: 11-of-11
Supported Languagesen
Model ArchitectureQwen3_5MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.10.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size248320
LoRA ModelYes
Errorsreplace

Best Alternatives to Qwen3.5 24.5B Reapped V1

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 Whittle 25B A3B256K / 49.9 GB6111
...n3.6 35B A3B Heretic REAP 0.30256K / 50.2 GB664
Note: green Score (e.g. "73.2") means that the model is better than groxaxo/Qwen3.5-24.5B-Reapped-v1.